Medical image analysis

A novel atlas-based segmentation approach based on the combination of multiple registrations is presented. Multiple atlases are registered to a target image. To obtain a segmentation of the target, labels of the atlas images are propagated to it. The propagated labels are combined by spatially varying decision fusion weights. These weights are derived from local assessment of the registration success. Furthermore, an atlas selection procedure is proposed that is equivalent to sequential forward selection from statistical pattern recognition theory. The proposed method is compared to three existing atlas-based segmentation approaches, namely (1) single atlas-based segmentation, (2) average-shape atlas-based segmentation, and (3) multi-atlas-based segmentation with averaging as decision fusion. These methods were tested on the segmentation of the heart and the aorta in computed tomography scans of the thorax. The results show that the proposed method outperforms other methods and yields results very close to those of an independent human observer. Moreover, the additional atlas selection step led to a faster segmentation at a comparable performance.

Multi-Atlas-Based Segmentation With Local Decision Fusion—Application to Cardiac and Aortic Segmentation in CT Scans

Nonrigid local image registration plays an important role in medical imaging. In this paper we focus on demon registration which is introduced by Thirion [1], and is comparable to fluid registration. Because demon registration cannot deal with multiple MRI modalities, we introduce a MRI modality transformation which changes the representation of a T1 scan into a T2 scan using the peaks in a joint histogram. We compare the performance between demon registration with modality transformation, demon registration with gradient images and Rueckerts [2] B-spline based free form deformation method in combination with mutual information. For this test we use perfectly aligned T1 and T2 slices from the BrainWeb database [3], which we local spherically distort. In conclusion demon registration with modality transformation gives the smallest registration errors, in case of local large spherical distortions and small bias fields.

/pdf/mri-modalitiy-transformation-in-demon-registration-le8d602bsz.pdf

MRI modalitiy transformation in demon registration

Deep brain stimulation therapy is an effective symptomatic treatment for Parkinson's disease, yet the precise mechanisms responsible for its therapeutic effects remain unclear. Although the targets of deep brain stimulation are grey matter structures, axonal modulation is known to play an important role in deep brain stimulation's therapeutic mechanism. Several white matter structures in proximity to the subthalamic nucleus have been implicated in the clinical benefits of deep brain stimulation for Parkinson's disease. We assessed the connectivity patterns that characterize clinically beneficial electrodes in Parkinson's disease patients, after deep brain stimulation of the subthalamic nucleus. We evaluated 22 patients with Parkinson's disease (11 females, age 57 ± 9.1 years, disease duration 13.3 ± 6.3 years) who received bilateral deep brain stimulation of the subthalamic nucleus at the National Institutes of Health. During an initial electrode screening session, one month after deep brain stimulation implantation, the clinical benefits of each contact were determined. The electrode was localized by coregistering preoperative magnetic resonance imaging and postoperative computer tomography images and the volume of tissue activated was estimated from stimulation voltage and impedance. Brain connectivity for the volume of tissue activated of deep brain stimulation contacts was assessed using probabilistic tractography with diffusion-tensor data. Areas most frequently connected to clinically effective contacts included the thalamus, substantia nigra, brainstem and superior frontal gyrus. A series of discriminant analyses demonstrated that the strength of connectivity to the superior frontal gyrus and the thalamus were positively associated with clinical effectiveness. The connectivity patterns observed in our study suggest that the modulation of white matter tracts directed to the superior frontal gyrus and the thalamus is associated with favourable clinical outcomes and may contribute to the therapeutic effects of deep brain stimulation. Our method can be further developed to reliably identify effective deep brain stimulation contacts and aid in the programming process.

/pdf/tractography-patterns-of-subthalamic-nucleus-deep-brain-4ybt145zkj.pdf

Tractography patterns of subthalamic nucleus deep brain stimulation

CranialVault and its CRAVE tools: a clinical computer assistance system for Deep Brain Stimulation (DBS) therapy

Active deformation fields: Dense deformation field estimation for atlas-based segmentation using the active contour framework

Objects In functional stereotactic neurosurgery, one of the cornerstones upon which the success and the operating time depends is an accurate targeting. The subthalamic nucleus (STN) is the usual target involved when applying deep brain stimulation for Parkinson’s disease (PD). Unfortunately, STN is usually not clearly visible in common medical imaging modalities, which justifies the use of atlas-based segmentation techniques to infer the STN location. Materials and methods Eight bilaterally implanted PD patients were included in this study. A three-dimensional T1-weighted sequence and inversion recovery T2-weighted coronal slices were acquired pre-operatively. We propose a methodology for the construction of a ground truth of the STN location and a scheme that allows both, to perform a comparison between different non-rigid registration algorithms and to evaluate their usability to locate the STN automatically. Results The intra-expert variability in identifying the STN location is 1.06±0.61 mm while the best non-rigid registration method gives an error of 1.80±0.62 mm. On the other hand, statistical tests show that an affine registration with only 12 degrees of freedom is not enough for this application. Conclusions Using our validation–evaluation scheme, we demonstrate that automatic STN localization is possible and accurate with non-rigid registration algorithms.

/pdf/validation-of-experts-versus-atlas-based-and-automatic-4guplpyfc4.pdf

Validation of Experts versus Atlas-based and Automatic Registration Methods for Subthalamic Nucleus Targeting on MRI

In the last five years, Deep Brain Stimulation (DBS) has become the most popular and effective surgical technique for the treatment of Parkinson’s disease (PD). The Subthalamic Nucleus (STN) is the usual target involved when applying DBS. Unfortunately, the STN is in general not visible in common medical imaging modalities. Therefore, atlas-based segmentation is commonly considered to locate it in the images. In this paper, we propose a scheme that allows both, to perform a comparison between different registration algorithms and to evaluate their ability to locate the STN automatically. Using this scheme we can evaluate the expert variability against the error of the algorithms and we demonstrate that automatic STN location is possible and as accurate as the methods currently used.

/pdf/cross-validation-of-experts-versus-registration-methods-for-47lqe8ue39.pdf

Cross validation of experts versus registration methods for target localization in deep brain stimulation

In functional stereotactic neurosurgery, one of the cornerstones upon which the success and the operating time depends is an accurate targeting. The subthalamic nucleus (STN) is the usual target involved when applying Deep Brain Stimulation (DBS) for the Parkinson's disease (PD). Unfortunately, STN is usually not clearly visible in common medical imaging modalities, which justifies the use of atlas-based segmentation techniques to infer the STN location. We propose a scheme that allows both, to perform a comparison between different non-rigid atlas registration algorithms and to evaluate their usability to locate the STN automatically. Using our validation–evaluation scheme and accurate registration algorithms, we demonstrate that automatic STN localization is possible and accurate.

/pdf/automatic-subthalamic-nucleus-targeting-for-deep-brain-4btnltplv6.pdf

F. Javier Sánchez Castro

Papers

Active deformation fields: Dense deformation field estimation for atlas-based segmentation using the active contour framework

Validation of Experts versus Atlas-based and Automatic Registration Methods for Subthalamic Nucleus Targeting on MRI

Cross validation of experts versus registration methods for target localization in deep brain stimulation

Automatic subthalamic nucleus targeting for deep brain stimulation. A validation study